Speech and Language Processing (3rd ed. draft)
Dan Jurafsky and James H. Martin

Here's our August 19, 2026 release!

  • This release finally has a chapter 1! Much LLM material from the former chapter 7 was decanted here, plus lots of new material to make this a fun intro chapter for students as well as other newcomers to the field.

  • The former chapter 8 (Transformers) was merged with the remainder of former chapter 7 (=pretraining and decoding/sampling) to create a new single chapter that covers transformers, pretraining, and decoding.

  • There is a large stub (about half) of an interpretability chapter 10, more to come on the next edition.

  • We used Claude Opus 5 to suggest more exercises for various chapters, and also to do a pass over the first 8 chapters to point out any bugs it could find. It found a lot. The result is some more exercises in this release, and also hopefully fewer typos and subtle notation inconsistencies to plague you the readers!
Individual chapters are below. The slides are not yet updated from the January release, we'll be doing that soon and will update this line when done

Here is a single pdf of Aug 19, 2026 book!

  1. Feel free to use the draft chapters and slides in your classes, print it out, whatever, the resulting feedback we get from you makes the book better!
  2. Typos and comments are very welcome (just email slp3edbugs@gmail.com and let us know the date on the draft)! (Don't bother reporting missing refs due to cross-chapter cross-reference problems in the indvidual chapter pdfs, those are fixed in the full book draft)
  3. Gratitude! We've put up a list here of the wonderful people who have sent so many fantastic suggestions and bug-fixes for improving the book. We are really grateful to all of you for your help, the book would not be possible without you!
  4. How to cite the book:

    Daniel Jurafsky and James H. Martin. 2026. Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition with Language Models, 3rd edition. Online manuscript released August 19, 2026. https://web.stanford.edu/~jurafsky/slp3.

  5. A bib entry for the book is here.
    @Book{jm3,
      author =       "Daniel Jurafsky and James H. Martin",
      title =        "Speech and Language Processing: An Introduction to Natural Language Processing, 
      		  Computational Linguistics, and Speech Recognition,
    		   with Language Models",
      year =         "2026",
      url = {https://web.stanford.edu/~jurafsky/slp3/},
      note = "Online manuscript released August 19, 2026",
      edition =         "3rd",
      }
    
  6. When will the book be finished? Don't ask.
  7. If you need the previous Jan 2026 draft chapters, they are here; If you need the previous Aug 2025 draft chapters, they are here;
     
Volume I: Large Language Models
Chapter Slides
1: Introduction
2: Words and Tokens 2: Words and Tokens [pptx] [pdf] 2: Edit Distance [pptx] [pdf]
3: N-gram Language Models 3: [pptx] [pdf]
4: Logistic Regression and Text Classification 4: [pptx] [pdf]
5: Embeddings 5: [pptx] [pdf]
6: Neural Networks 6: [pptx] [pdf]
7: Transformers and Pretraining 7: LLM (needs refactoring): [pptx] [pdf] Transformer [pptx][pdf]
8: Post-training
 
Volume II: Advanced LLM Topics and Tools
Chapter Slides
9: Masked Language Models 9: [pptx] [pdf]
10: Interpretability
11: Information Retrieval and RAG 11: [pptx] [pdf]
12: Agents [not written yet]
13: Machine Translation
14: RNNs and LSTMs 13: [pptx] [pdf]
15: Phonetics and Speech Feature Extraction
16: Automatic Speech Recognition
17: Text-to-Speech
 
Volume III: Annotating Linguistic Structure
Chapter Slides
18: Sequence Labeling for Parts of Speech and Named Entities 18: (Intro only) [pptx] [pdf]
19: Context-Free Grammars and Constituency Parsing
20: Dependency Parsing
21: Information Extraction: Relations, Events, and Time
22: Semantic Role Labeling and Argument Structure
23: Lexicons for Sentiment, Affect, and Connotation
24: Coreference Resolution and Entity Linking
25: Discourse Coherence
26: Conversation and its Structure
 
Appendix (will be just on the web)
A: Hidden Markov Models
B: Naive Bayes Classification B: [pptx] [pdf]
C: Kneser-Ney Smoothing
D: Spelling Correction and the Noisy Channel
E: Statistical Constituency Parsing
F: Context-Free Grammars
G: Combinatory Categorial Grammar
H: Logical Representations of Sentence Meaning
I: Word Senses and WordNet
J: PPMI
K: Frame-based Dialogue Systems